Upload PPO LunarLander-v2 trained agent

LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad7f89b22ff12f8d41a4570fa033dd2b34b32a13a8ea56a572a1f88b6195cc1f
+oid sha256:a1e42a2aa17ab4e116503b01e2d0508b2a56c014ed2f807d2f6697c26ce6c9fc
 size 462520

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 296.24 +/- 24.43
+      value: 285.85 +/- 20.67
       name: mean_reward
       verified: false
 ---

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d306dc191f0726fca06ecc6bca26eeb339cd204cebbfe9c226c0ec436297e4e9
-size 143079
+oid sha256:bac3f3636be74137ca56acb7dafcf81e17e7a724f862bc7fd007a2ac079b1f26
+size 157751

results.json

@@ -1 +1 @@
-{"mean_reward": 296.2370421156669, "std_reward": 24.432612978757028, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T10:10:47.364133"}
+{"mean_reward": 285.8485228534459, "std_reward": 20.667869439955002, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T10:12:13.767058"}